def fullAnalysis(location,file,mt):
data=pd.read_csv(location+'/'+file)
data=f.getDummyVarPositionForK(data,1)
data=f.cleanDataMatrix(data,withNull=True)
X,y_,initNum,D=f.createCovarsAndProbVectorForMutationType(data,mt)
features=X.columns[1:]
sigList=featureSelectionPairs(X, y_, initNum, features)
analyze(X, y_, initNum, stepNum=400000,plot=False,v=0.1)
def fullAnalysis(location,file,mt):
"""
size=256
initNum=np.random.poisson(lam=1000000,size=size)
data=pd.read_csv(r'C:\Users\Guyling1\ContextProject\SABIN\regressionCSVOneFileCountsK5P7.csv')
data=f.getDummyVarPositionForK(data,1)
data=f.cleanDataMatrix(data,withNull=True)
covariates=f.createCovarsAndProbVectorForMutationType(data,'CT')[0]
covariates=np.matrix(covariates)[:,1:]
pinit=np.ones(size)*-11
X=covariates
#print covarMatrix.shape
realBeta=np.random.multivariate_normal(np.zeros(covars),np.identity(covars))#
realBeta[0]=3
realBeta[1]=-3
#realBeta[-1]=-5
realGamma=np.zeros(covars)
realGamma[0]=1
realGamma[1]=1
#realGamma[-1]=1
betaGamma=realBeta*realGamma
print X
means=pinit+np.dot(X,betaGamma)
means=sc.special.expit(means)
#print means[:100]
y_=np.random.binomial(initNum,means)
y_=y_/initNum
#print y_
#print y_[0:100]
#Split Data
#X_tr, X_te, y_tr, y_te,initNum_tr,initNum_te = train_test_split(X,y_,initNum,test_size=0.25, random_state=0)
"""
#location=r'C:\Users\Guyling1\Documents\guyReserch\\'
#'/sternadi/home/volume1/guyling/MCMC/'
data=pd.read_csv(location+'/'+file)
data=f.getDummyVarPositionForK(data,1)
data=f.cleanDataMatrix(data,withNull=True)
X,y_,initNum,D=f.createCovarsAndProbVectorForMutationType(data,mt)
#D.to_csv(r'C:\Users\Guyling1\Documents\guyReserch\testFeatures.csv')
#outputFile='C:\Users\Guyling1\ContextProject\MCMC\P7K5_{}.csv'.format(mt)
features=X.columns[1:]
print len(features)
#print features
sigList=featureSelectionPairs(X, y_, initNum, features)
#print sigList
#featureListToGraphMatrix(sigList, features)
#featureSelection(X, y_, initNum, features, sigList )
#analyzeSigFeatuesByCorrelation(X, y_, initNum, sigList, features)
analyze(X, y_, initNum, stepNum=400000,plot=False,v=0.1)
#fullAnalysis()
def loadData(dataPath, mutType):
data = pd.read_csv(dataPath)
name = ".".join(dataPath.split("/")[-1].split(".")[:-1]) + "_" + mutType
folder = "/".join(dataPath.split("/")[:-1])
data = f.getDummyVarPositionForK(data, 2)
data = f.cleanDataMatrix(data, withNull=True)
X, y, initNum, D = f.createCovarsAndProbVectorForMutationType(
data, mutType)
features = X.columns[1:]
X = np.matrix(X)[:, 1:]
n, m = X.shape
y = np.array((y * initNum), dtype=int).reshape(n, 1)
initNum = np.array(initNum).reshape(n, 1)
return X, y, initNum, features, name, folder
def analyseSample(location, file,oldNuc=1,newNuc=3):
data=pd.read_csv(location+file)
data=f.getDummyVarPositionForK(data,2)
data=f.cleanDataMatrix(data,withNull=True)
X,y_,initNum,D=f.createCovarsAndProbVectorForMutationType(data,NUCS[oldNuc]+NUCS[newNuc])
features=X.columns[1:]
sigList=mcmc.featureSelectionPairs(X, y_, initNum, features)
if len(sigList)>0:
sigFeatures,resultSummary=mcmc.featureSelection(X, y_, initNum, features, sigList,name=file+"_old:{}_new:{}_".format(NUCS[oldNuc],NUCS[newNuc]))
sigFeatures=features[[s[0] for s in sigFeatures]]
out=open(location+file+"_old:{}_new:{}_sigFeatures.out".format(NUCS[oldNuc],NUCS[newNuc]),'w')
for s in sigFeatures:
out.write(str(s)+"\n")
out.close()
resultSummary.to_csv(location+file+"_old:{}_new:{}_resultSummary.csv".format(NUCS[oldNuc],NUCS[newNuc]))
else:
out=open(location+file+"_old:{}_new:{}_sigFeatures.out".format(NUCS[oldNuc],NUCS[newNuc]),'w')
out.write("#no sig features in the initial stage")
pass
def analyseSample(file, oldNuc=1, newNuc=3):
location = '/sternadi/home/volume1/guyling/MCMC/dataSimulations/'
data = pd.read_csv(location + file)
data = f.getDummyVarPositionForK(data, 2)
data = f.cleanDataMatrix(data, withNull=True)
X, y_, initNum, D = f.createCovarsAndProbVectorForMutationType(
data, NUCS[oldNuc] + NUCS[newNuc])
features = X.columns[1:]
#sigList=[3, 8, 9, 10, 28, 32, 33, 34, 36, 37, 38, 40, 41, 42, 46, 62, 63, 65, 66, 69, 73, 74, 78, 99, 100, 101, 103, 104, 105, 106, 107]
sigList = mcmc.featureSelectionPairs(X, y_, initNum, features)
print sigList
if len(sigList) > 0:
sigFeatures, resultSummary = mcmc.featureSelection(
X,
y_,
initNum,
features,
sigList,
name=file + "_old:{}_new:{}_".format(NUCS[oldNuc], NUCS[newNuc]))
print sigFeatures
sigFeatures = features[[s[0] for s in sigFeatures]]
out = open(
location + file + "_old:{}_new:{}_sigFeatures.out".format(
NUCS[oldNuc], NUCS[newNuc]), 'w')
for s in sigFeatures:
out.write(str(s) + "\n")
out.close()
resultSummary.to_csv(location + file +
"_old:{}_new:{}_resultSummary.csv".format(
NUCS[oldNuc], NUCS[newNuc]))
else:
out = open(
location + file + "_old:{}_new:{}_sigFeatures.out".format(
NUCS[oldNuc], NUCS[newNuc]), 'w')
out.write("#no sig features in the initial stage")
pass